# Claude 3 Haiku vs Qwen3 Max

> Qwen3 Max is the stronger model overall, scoring 43.5 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-qwen3-max
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 Max leads 62.6 to 29.8.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 97.1% for Qwen3 Max.

## Snapshot

| | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.7 | 43.5 |
| Rank | 333 | 82 |
| Context | — | 262K |
| Input $/M | — | $1.20 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Qwen3 Max: 42.4 (#93)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1199 | 1456 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 370.45 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Qwen3 Max: —

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Qwen3 Max: 22.0 (#186)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 72.5% |
| LMArena Hard Prompts | 1174 | 1448 |
| DTBench | 50.1% | 82.1% |
| LMCA | 8.8% | 28.3% |
| Epoch Capabilities Index | 118.3 | 142.41 |
| NYT Connections (extended) | — | 30.1% |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Qwen3 Max: 37.6 (#94)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 73.3% |
| LMArena Math | 1188 | 1447 |
| MATH Level 5 | 14.9% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Qwen3 Max: 48.1 (#72)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 36.3% | 72.6% |
| LMArena Expert | 1148 | 1457 |
| SimpleQA Verified | — | 48.7% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Qwen3 Max: —

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Qwen3 Max: 53.9 (#58)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1178 | 1429 |
| LMArena Chinese | 1155 | 1479 |
| LMArena French | 1194 | 1450 |
| LMArena German | 1174 | 1463 |
| LMArena Japanese | 1102 | 1399 |
| LMArena Korean | 1108 | 1397 |
| LMArena Russian | 1204 | 1428 |
| LMArena Spanish | 1165 | 1463 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Qwen3 Max: 75.0 (#81)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1174 | 1420 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Qwen3 Max: 41.6 (#129)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1191 | 1439 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Qwen3 Max: 62.6 (#72)

| Benchmark | Claude 3 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Text | 1195 | 1439 |
| LMArena Creative Writing | 1157 | 1401 |
| LMArena Multi-Turn | 1190 | 1446 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.5 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 42.4 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Qwen3 Max share?

24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3 Max has 33.